What are Convolutional Neural Networks (CNNs)?

Поділитися
Вставка
  • Опубліковано 26 січ 2025

КОМЕНТАРІ • 152

  • @sunnygan90
    @sunnygan90 3 роки тому +223

    Unbelievably clear and succinct explanations

    • @IBMTechnology
      @IBMTechnology  3 роки тому +24

      Thanks for the appreciation, Sunny, that's what we strive for! 🙂

    • @JockGeez
      @JockGeez Рік тому +1

      Well said

    • @Baileyreads10
      @Baileyreads10 6 місяців тому

      L.
      .
      מצורף .
      ...
      ❤, . מחלת תינו​@@JockGeez

  • @arrahul316
    @arrahul316 2 роки тому +35

    The intro just rocked, as to why CNN. "Humans can do object detection quickly and machines can't" and hence that's where it begins. Amazing... Thanks...

  • @ameridev
    @ameridev 2 роки тому +31

    Explained in a very simple way that's easy to understand! Great video!

  • @jiajunmak4039
    @jiajunmak4039 3 роки тому +19

    Bro this dude just wrote mirrored wth. Also thanks for the video! The concept of CNN is a lot more clear to me now. :))

    • @IBMTechnology
      @IBMTechnology  3 роки тому +13

      Glad this was useful to you! 👍 As for writing mirrored, here is how we do it 👉 ibm.co/3jnq1st 😉

  • @simonrashid-po4zq
    @simonrashid-po4zq 8 місяців тому +5

    man i like how you clearly explain your videos

  • @rdbnair1445
    @rdbnair1445 2 роки тому +16

    Have been watching several videos to get a high level understanding of CNN, but no luck. However, this is a very good explanation ! Cleared lots of doubt in few minutes. Thank you

  • @MrMMF94
    @MrMMF94 Рік тому +10

    Such a likeable person explaining so well, much appreciated! :)

  • @kaysonargyle
    @kaysonargyle 9 місяців тому +25

    Mans just wrote in perfect handwriting BACKWARDS on the glass and no one is talking about it what the heck

    • @emmanueljohn4178
      @emmanueljohn4178 7 місяців тому +22

      um actually the video
      is mirrored

    • @CristhianDalmazzo
      @CristhianDalmazzo 6 місяців тому +2

      The magic of video editing, he’s a wizard

    • @jgcornell
      @jgcornell 5 місяців тому

      If you look around, you'll find a video they made to address just this question, everyone who watches IBM videos asks exactly that, I know I did :)

    • @amritbhattarai5083
      @amritbhattarai5083 2 місяці тому

      Its an easy solution actually. The video is recorded from the other side of the glass board. The video is then flipped horizontally. You can observe the watch appears to be on his right hand but its actually left.

  • @pellythirteen5654
    @pellythirteen5654 2 роки тому +29

    In my eyes , the goal of Convolution is to make the signal invariant to scaling and translation. It acts as a pre-processor of the raw input signal. You could also first pre-process your training set and store it in a file. Then you can use this file and feed it directly to the deep neural network. You don't need the Convolution anymore at training.
    Another way of making your signal (picture) invariant is to first Fourier Transform it to make it scaling and translation invariant. Next you transform the signal from cartesian to polar coordinates to make it rotational invariant. Finally you Fourier Transform that signal and end up with a fully invariant signal that you can store as a pre-processed Training set.

    • @sourabhsoni3988
      @sourabhsoni3988 2 роки тому +3

      Any citations for elaborating what you said.

    • @pietjan2409
      @pietjan2409 Рік тому +1

      But CNN makes it possible to sequentially apply more abstract filters that fit the specific objects in the image. I'm not sure if those transformations you named are able to do that, which is taking very complex and abstract patterns into account.

  • @minnaazmy6710
    @minnaazmy6710 7 місяців тому +1

    This channel has some of the best CompSci explanations ! Never been disappointed!

  • @africa_revealed
    @africa_revealed Місяць тому

    I was smiling to myself the whole time. So simple and succinct! Thank you

  • @jesprotech
    @jesprotech 3 місяці тому +1

    I was looking to understand how to represent a CNN in a way that clearly shows the difference to just dense neural networks. This really helped! thanks!

  • @andresinho83
    @andresinho83 3 роки тому +7

    0:42 I cannot get over the fact that this dude just wrote the term CNN backwards so easily and so fast :O

    • @andresinho83
      @andresinho83 3 роки тому +4

      Or maybe he just inverted the video horizontally in post edition

    • @frankbik1063
      @frankbik1063 3 роки тому

      try looking at the video using a mirror ...

    • @badbud804
      @badbud804 Рік тому +3

      He inverted the video. That's why he's writing with his left hand and wearing his clock on the right arm.

    • @andresinho83
      @andresinho83 Рік тому +1

      ​@@badbud804yeah, I also mentioned that but it would be very impressive if he could actually do that

    • @pruthweeshasalian3688
      @pruthweeshasalian3688 2 місяці тому

      the knob/button on the watch (which is typically to the right of the dial/screen) is the most unambiguous clue establishing the video is mirrored.

  • @P400hse
    @P400hse 7 місяців тому

    This is probably the best explained video i've ever watched, you're a great tutor!!!!!😍😍

  • @moonstone6071
    @moonstone6071 Рік тому

    Fantastic explanation! Very pedagogical and easy to follow. Thank you!

  • @emc3000
    @emc3000 Рік тому

    Dear lord this is perfectly chunked information.

  • @Traxin027
    @Traxin027 9 місяців тому

    Martin, you are a superb teacher. You make learning easy and fun.

  • @tjunohambeka1938
    @tjunohambeka1938 Рік тому +1

    This was easy to understand and very concise...Thank you

  • @m.g.4805
    @m.g.4805 4 місяці тому +4

    Amazing explanation!
    Two quick questions:
    1. If each layer of a neural network can recognize more complex / abstract objects, does that mean that deeper neural networks (neural networks with more layers) will always be more powerful, or at least have the potential to be more powerful?
    2. Could one say the same about the width of neural networks? Would a neural network with more nodes per layer be able to recognize a larger variety of images?

    • @pruthweeshasalian3688
      @pruthweeshasalian3688 2 місяці тому

      Both those assumptions are valid, with some caveats.
      If you have too many nodes in a layer, you're looking for too many features in the data, and you'd virtually memorise the training data after some point, because you're not reducing the dimensionality anymore.
      If you use too many layers, you're risking vanishing/exploding gradients, and you're making features needlessly complex, which may also lead to overfitting.
      Besides, there need to be sufficiently complex activation functions between layers to leverage the feature-extracting prowess prowess of each node. If the activation functions are too non-linear, the individual weights become less meaningful, and harder to train. If the activation function is not sufficiently non-linear, you're essentially obtaining the result of single matrix multiplication operation with the computational overhead of multiple operations.

  • @karthik-ie1zj
    @karthik-ie1zj 7 місяців тому

    you are more and more better than my clg faculty thank you for a great a explanation 😍

  • @mohamedvawda979
    @mohamedvawda979 2 роки тому +2

    This explanation was so good. Currently using CNNs for remote sensing applications.

  • @jeremypatton8204
    @jeremypatton8204 6 місяців тому

    Nice series Marvin 😁

  • @herosoftheworld7
    @herosoftheworld7 6 місяців тому

    Very excellent explanation ❤

  • @nirbhaykumarchaubey8777
    @nirbhaykumarchaubey8777 Місяць тому

    I understood it very well, in case som1 didn't, watch this video after watching 3b1b video on neural networks

  • @anabucchi9003
    @anabucchi9003 6 місяців тому

    best teacher!! 👏

  • @imohrufus
    @imohrufus 4 місяці тому

    there should be a full course on this neural network taught by Martin

  • @vinadiscar5236
    @vinadiscar5236 3 роки тому +3

    You made it easy to understand. Very helpful. Thanks a lot :)

  • @michaelkaercher
    @michaelkaercher 7 місяців тому

    Very good explaination. Thank you.

  • @ayushmohanty4123
    @ayushmohanty4123 Рік тому

    I have a question how are the levels of filters are defined ?

  • @0xabaki
    @0xabaki 11 місяців тому

    amazing as usual.

  • @EmTechCySecEdu
    @EmTechCySecEdu 6 місяців тому

    Thanks. Great learning Video.

  • @jzhao1562
    @jzhao1562 7 місяців тому

    Fantastic Video. Is Martin always writing mirrored? I am fastinated by how your video recording works!

  • @nassimaguenaoui3776
    @nassimaguenaoui3776 Рік тому +1

    Very clear and right-to-the-point explanation! Thank you!

  • @Goalkeeper143
    @Goalkeeper143 2 роки тому

    Utterly well done, our IBM ML specialist!

  • @kitrt
    @kitrt 3 роки тому +7

    Hi! Have I assumed correctly that in case of using CNNs for image recognition, the deeper the filters go, the more they zoom out on the image?
    Next logical question is - what type of software is used to analyze test cases (e.g. real houses) and create those filters?

    • @ydl6832
      @ydl6832 Рік тому

      The filter is no more than just a matrix. The discrete convolution is performed in each layer (this is where the name CNN comes from). The filter is refined using training data, just like how you would train a perception, you train the matrix to behave as desired.

  • @akmalyafi1470
    @akmalyafi1470 2 роки тому

    Hello, thank you for the explanation but I still don't understand how the filters are made.

  • @consyyrd
    @consyyrd 11 місяців тому

    So I take the key to building a CNN is on how to build the filters? also, given that the first layer is fragmented, does it mean that the first layer could be of general usage, while the later layers are more application oriented?

  • @mona-xf5mr
    @mona-xf5mr 5 місяців тому

    love this explanation ...

  • @bryantea2039
    @bryantea2039 3 роки тому +5

    Well if the beer videos ever stop Martin you have a career in IT Vlogging 😁

  • @namadivinodkumar9755
    @namadivinodkumar9755 2 роки тому

    Can we implement this CNN to determine micro-level profiles, i.e., micrometer level?

  • @basedmatt
    @basedmatt 2 роки тому

    What would be the difference between the standard convolutional networks and something newer like CLIP?

  • @19AKS58
    @19AKS58 4 місяці тому

    Martin, how are the filters for a CNN created? Random? stored in some database? Might there be advantage from specifying filters yourself, particularly if you have expertise with the domain the images are from ?

  • @ghostofvalor
    @ghostofvalor Місяць тому

    Damn that was crystal clear.

  • @nehaskulkarni
    @nehaskulkarni 11 місяців тому

    such an easy, clear and to the point explanation! thanks a lot

  • @JockGeez
    @JockGeez Рік тому

    This guy gives crystal clear explanations. Supremely Clear!

  • @bran_rx
    @bran_rx 2 роки тому

    this video hits different if you are currently taking digital image processing course. I feel smart lol

  • @rogerfed2030
    @rogerfed2030 11 місяців тому

    is this what the vision pro uses?

  • @meryamelqamary7638
    @meryamelqamary7638 Рік тому

    Hi ,I'm a maths student and I need to do a project. the theme is games and sport. I saw your video and thought why not apply this technique to the world of sports? to discover from the analysis of the players' movements if one is sick. Can you help me to apply CNN and use it well please.

    • @John-wx3zn
      @John-wx3zn 9 місяців тому

      Don't ask him. His explaination is sloppy and incomplete. The convolution operations with the filters produce matrix channels building the tensor. For example after four convolution operations, you should have four matrix channels. The next operation would be a max pooling operation on each matrix channel in the tensor. Please let me know if you have a question.

  • @YazanAlManasir
    @YazanAlManasir 2 роки тому

    thanks martin for the clear explanations
    you are amazing

  • @ANIF_CYMBOLIC
    @ANIF_CYMBOLIC 8 місяців тому

    Identifying, organizing and reaping to thought.
    Your tv CAN communicate with you via your neurons producing electromagnetic waves

  • @JamesAuger-t9o
    @JamesAuger-t9o Рік тому

    Explained this video very well - highly recommend! Thank you

  • @lordoftherain
    @lordoftherain Рік тому

    so by combining the other video of yours. At the end of the the CNN there will be a discriminator which has been trained to know what a house looks like, what an apartment looks like, what a skyscraper looks like and therefore tells you that is a house ?

  • @enfermagemporummundomelhor6499
    @enfermagemporummundomelhor6499 7 місяців тому

    certo, curiosidade: Se tratando de pessoas gêmeas ou sei lá trigêmeas univitelinos como diferencia-las pela CNN? Outro detalhe com relação aos filtros, suponhamos que temos objetos sobre as retas por exemplo como identifica-las neste processo com tão vastas imagens possíveis de armazena-las?

  • @crazymonkey5381
    @crazymonkey5381 3 роки тому +2

    clearly understandable 🙏🙏🙏

  • @bellofolaniyi5546
    @bellofolaniyi5546 Місяць тому

    Highly insightful

  • @jimj2683
    @jimj2683 Рік тому

    Doesn't it require a lot of manual work to make all those filters? Isn't it better to just run everything through a regular neural network?

    • @pruthweeshasalian3688
      @pruthweeshasalian3688 2 місяці тому

      That's the neat part - you don't manually make those filters. Those filters are learned by the network based on bounding boxes in the annotated training images.

  • @pierQRzt180
    @pierQRzt180 2 роки тому

    The volume is a bit quiet here.

  • @elmoreglidingclub3030
    @elmoreglidingclub3030 Рік тому

    Great explanation! Great job; thanks!

  • @Yewbzee
    @Yewbzee Рік тому +1

    Machine learning is truly amazing yet it pales into insignificance when compared to the ability of this chap to write backwards.

    • @capitão_paçoca
      @capitão_paçoca 8 місяців тому

      I cant tell whether you're joking, but I think the video is flipped horizontally

  • @saadat_ic
    @saadat_ic Рік тому

    This explanation is good. Thanks. 😊

  • @studywithmaike
    @studywithmaike Рік тому

    Great video! Thanks 👍🏼

  • @ksatriabaja
    @ksatriabaja 2 місяці тому

    Thanks really helpful

  • @JackMacyntire
    @JackMacyntire 5 місяців тому

    At last a video that is useful!

  • @praphulshaw2128
    @praphulshaw2128 Рік тому

    What kind of bord do u use to write

  • @kaviarasu.thuraiarasu89
    @kaviarasu.thuraiarasu89 2 роки тому

    Superb explaination

  • @monome3038
    @monome3038 Рік тому

    great work explaining!

  • @paskalisnani
    @paskalisnani 3 роки тому

    Thank you

  • @krishnapayneeandy2016
    @krishnapayneeandy2016 2 роки тому

    Application of successive Convolutional Filters well presented but at a high level only

  • @elenapotapova624
    @elenapotapova624 10 місяців тому

    finally ! bravo. clear and concise

  • @nazrinibrahimli7042
    @nazrinibrahimli7042 Рік тому

    The best explanation ever.

  • @thehappygravedigger
    @thehappygravedigger Рік тому

    Awesome explanations ! ... thank you for sharing your knowledge ;))

  • @alihankaya9183
    @alihankaya9183 Рік тому +1

    Will the Activation Functions video come?

  • @michaelmcwhirter
    @michaelmcwhirter 10 місяців тому

    Great video 🔥

  • @benscott8614
    @benscott8614 Рік тому +1

    Is he writing backwards...! impressive

  • @JoaoAssalim
    @JoaoAssalim Рік тому

    Very good explanation!

  • @RaselAhmed-ix5ee
    @RaselAhmed-ix5ee 3 роки тому

    can you help me regarding my project "human pose estimation"

    • @IBMTechnology
      @IBMTechnology  3 роки тому

      Hi Rasel! What sort of help would you need? 🙂

    • @RaselAhmed-ix5ee
      @RaselAhmed-ix5ee 3 роки тому

      @@IBMTechnology i have to detect human pose estimation through skeletal data extracted from it

  • @rajhanravi
    @rajhanravi Рік тому

    Wow such a comprehensive content on CNN!

  • @rubenhanjrahing7324
    @rubenhanjrahing7324 Рік тому

    oh my god, thankyou for the explanation. Easy to understand

  • @biswajitrout4710
    @biswajitrout4710 3 роки тому

    Great content

  • @snowykoyuki
    @snowykoyuki Рік тому +77

    This is too low level and vague for people who need it and too high level and complicated for children, I believe that you should go more in depth to provide more information such as how the convolution works, different activation methods and different types of layers

    • @ydl6832
      @ydl6832 Рік тому +16

      It is just an introduction. If one wants to learn the details, they can search for textbooks, I believe there are countless available.

    • @aaroncroft7514
      @aaroncroft7514 Рік тому +7

      Then actually go and study CNNs. This is a brief overview of how they work.

    • @allenabishek1478
      @allenabishek1478 Рік тому +7

      These videos are for 2 demographics, young adults/teenagers who find AI technology fascinating and want to understand how it works. And for children to spark the flame of the scientist inside them towards AI development when they grow up. The Second reason is the most important.

    • @sukritthakur1362
      @sukritthakur1362 4 місяці тому +4

      I genuinely needed a 2 minute explanation of this term and a few others. I guess I'm the target audience.

  • @void1185
    @void1185 Рік тому

    amazing work. thank u!

  • @austinbao
    @austinbao Рік тому

    perfect explanantion. I hate it when people throw difficult terms around. Why can't it be precise and clear such as using a house as an analogy. Well done!

  • @albuslee4831
    @albuslee4831 10 місяців тому

    This was so great thank you

  • @IngeniousDimensions369
    @IngeniousDimensions369 3 роки тому

    More please ☺️☺️

    • @IBMTechnology
      @IBMTechnology  3 роки тому

      Definitely what we're planning! 😀 In the meantime, feel free to subscribe to get notified of when we post more videos.

  • @tomitomi7941
    @tomitomi7941 5 місяців тому

    Thank you :)

  • @MaxXFalcon
    @MaxXFalcon Рік тому

    It's just like our brain recognises objects. Can we make conscious using this technique? Probably yes in future

  • @shunmugapriyamc4522
    @shunmugapriyamc4522 2 роки тому

    Waiting to learn more from you

  • @MaryJoseph19
    @MaryJoseph19 2 місяці тому

    thank you :)

  • @divyakumar8147
    @divyakumar8147 4 дні тому

    thanks sir

  • @DataScienceAI-rf4kx
    @DataScienceAI-rf4kx Рік тому

    clear and concise bigger picture of CNN

  • @mubashir22ful
    @mubashir22ful Рік тому

    Funny guy. Love him

  • @jeanpeuplu3862
    @jeanpeuplu3862 2 роки тому

    AWESOME! Thanks :)

  • @mzimmerman1988
    @mzimmerman1988 8 місяців тому

    thanks

  • @МихаилКуляпин-щ8л
    @МихаилКуляпин-щ8л 3 роки тому

    Thanks a lot!

  • @MegaMey1234
    @MegaMey1234 10 місяців тому

    All I can think of is... that how good he is in writing everything mirrored....

  • @chaoukimachreki6422
    @chaoukimachreki6422 3 роки тому

    This man rocks 🤘

  • @subodhi6
    @subodhi6 3 роки тому

    Thank you..!!

  • @typingcat
    @typingcat Рік тому

    Wait, that's a house? I thought it was the head of a tin robot.

  • @danyroby8471
    @danyroby8471 8 місяців тому

    that was a simple wow,,,,

  • @alexandre2245
    @alexandre2245 3 роки тому

    amazing